Complexity of the homomorphism problem parameterized by treewidth
Complexity of the homomorphism problem parameterized by treewidth
The homomorphism problem
Input: a graph
in , a graph in Output: decide if there is a homomorphism from
to , i.e., a mapping from the vertices of to those of such that, for any edge of , is an edge of .
For each
Here are some things that I found about the
- http://www.sciencedirect.com/science/article/pii/009589569090132J: If
is bipartite then is in PTIME, otherwise it is NP-complete, but of course the NP-hardness relies on allowing arbitrary . - http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.86.9013&rep=rep1&type=pdf: If the treewidth of
(modulo homomorphic equivalence) is bounded by a constant then is in PTIME (and otherwise it isn't, assuming FPT != W[1]). Hence, in particular my problem is in PTIME for fixed , but this doesn't tell me what is the dependency on the parameter. - From Flum and Grohe's book Parameterized Complexity Theory , Corollary 13.17: The problem
is FPT when parameterized by the size of (but I am parameterizing by the treewidth) - http://users.uoa.gr/~sedthilk/papers/homo.pdf, Corollary 3.2: When fixing a specific graph
, the problem , parameterized by k, is FPT (this even holds for more complicated counting variants), but I do not want to restrict to fixed .
K2-Think
The problem of determining the existence of a homomorphism from a graph ( G ) to a graph ( H ), where both ( G ) and ( H ) have treewidth at most ( k ), parameterized by ( k ), is known to be W[1]-hard.
Key Reasoning:
- Problem Definition: The homomorphism problem ( \text{Hom}(T_k, T_k) ) asks whether there exists a mapping ( h: V(G) \to V(H) ) preserving edges, given (...
GPT-5
Short answer: Hom(Tk, Tk) is W[1]-hard (indeed W[1]-complete) when parameterized by k. In particular, although for every fixed k the problem is solvable in polynomial time (XP), there is no f(k)·nO(1)-time algorithm unless FPT = W[1]. Moreover, under ETH there are matching lower bounds ruling out substantially faster FPT runtimes.
Why W[1]-hard
- A convenient source of hardness is Partitioned (a....
o4 mini
Below is what is known (and not known) about the two‐sided tree–width–parameterized homomorphism problem
Input: two graphs G,H with tw(G)≤k and tw(H)≤k
Parameter: k
Question: is there a homomorphism h:V(G)→V(H)?
- A trivial XP–algorithm.
– First run Bodlaender’s FPT‐algorithm to find (nice) tree‐decompositions of G and of H in time f₁(k)·(|G|+|H|).
– Then do...
Gemini 2.5 Pro
Excellent question. This is a classic problem in parameterized complexity that sits at the intersection of structural graph theory and logic.
The short answer is: The problem
Let's break down why this is the case, building on the results you've already found.
The XP Upper Bound
You correctly found the result...
o3 Pro
Let
p–HOM(Τk , Τk ) = {(G , H , k) | tw(G) ≤ k , tw(H) ≤ k , there is a graph–homomorphism h : G → H }
and take k to be the parameter.
We show that p–HOM(Τk , Τk ) is fixed–parameter tractable (FPT).
In fact one can decide the existence of the homomorphism in
f(k) · (|V(G)| + |V(H)|)ᴼ(1) time,
with f(k) = (k+1)^{(k+1)²}.
Thus the problem is in FPT and (unless FPT = W[1]) it ...
DeepSeek R1
Recall that FPT means that the problem can be solved in time f(k) * poly(n) for some computable function f, where n is the input size.
From the provided references and known res...
o3
The problem
p -HOM(𝒯k ,𝒯k )
Input : two graphs G,H with tw(G)≤k and tw(H)≤k
Parameter : k
Question : is there a homomorphism h : V(G)→V(H) ?
is fixed-parameter tractable. A simple dynamic–programming procedure that works simultaneously on tree–decompositions of G and H gives a running time of the form
f(k)·(|V(G)|+|V(H)|)O(1) ,
hence FPT. Below is a concrete algorithm and a sho...
Claude 3.7 Sonnet
Complexity of the Homomorphism Problem Parameterized by Treewidth
This question asks about the parameterized complexity of the graph homomorphism problem where both the source and target graphs have bounded treewidth.
Analysis of the Problem
The homomorphism problem
Claude Opus 4
This is an excellent question about the parameterized complexity of the graph homomorphism problem when both the source and target graphs have bounded treewidth.
The Answer
The problem
Key Results
The W[1]-hardness was established by Marx in his paper "Can You Beat Treewidth?" (FOCS 2007, Theory of Computin...
You need to be logged in to submit an answer